In this project we analyze the Covid-19 situation in India based on the data published on 21-Aug-2021

import zipfile
with zipfile.ZipFile("archive.zip","r") as zip_ref:
    zip_ref.extractall()

import pandas as pd
dataset = pd.read_csv('Latest Covid-19 India Status.csv', low_memory = False)
print(dataset.shape)
dataset.head(3)

(36, 8)

	State/UTs	Total Cases	Active	Discharged	Deaths	Active Ratio (%)	Discharge Ratio (%)	Death Ratio (%)
0	Andaman and Nicobar	7560	10	7421	129	0.13	98.16	1.71
1	Andhra Pradesh	2004590	13677	1977163	13750	0.68	98.63	0.69
2	Arunachal Pradesh	52409	1127	51023	259	2.15	97.36	0.49

dataset.columns = dataset.columns.str.replace(' ','_')

dataset.head(3)

	State/UTs	Total_Cases	Active	Discharged	Deaths	Active_Ratio_(%)	Discharge_Ratio_(%)	Death_Ratio_(%)
0	Andaman and Nicobar	7560	10	7421	129	0.13	98.16	1.71
1	Andhra Pradesh	2004590	13677	1977163	13750	0.68	98.63	0.69
2	Arunachal Pradesh	52409	1127	51023	259	2.15	97.36	0.49

dataset = dataset.rename(columns={"State/UTs":"State_UTs"})
dataset = dataset.rename(columns={"Active_Ratio_(%)":"Active_Ratio"})
dataset = dataset.rename(columns={"Discharge_Ratio_(%)":"Discharge_Ratio"})
dataset = dataset.rename(columns={"Death_Ratio_(%)":"Death_Ratio"})

dataset.head(3)

	State_UTs	Total_Cases	Active	Discharged	Deaths	Active_Ratio	Discharge_Ratio	Death_Ratio
0	Andaman and Nicobar	7560	10	7421	129	0.13	98.16	1.71
1	Andhra Pradesh	2004590	13677	1977163	13750	0.68	98.63	0.69
2	Arunachal Pradesh	52409	1127	51023	259	2.15	97.36	0.49

dataset["State_UTs"].count()

36

dataset.sort_values(["Active"], ascending=False)
# dataset.head(5)

	State_UTs	Total_Cases	Active	Discharged	Deaths	Active_Ratio	Discharge_Ratio	Death_Ratio
16	Kerala	3851984	159870	3672357	19757	4.15	95.34	0.51
20	Maharashtra	6432649	53260	6243034	136355	0.83	97.05	2.12
15	Karnataka	2941026	19810	2884032	37184	0.67	98.06	1.26
30	Tamil Nadu	2604074	18603	2550710	34761	0.71	97.95	1.33
1	Andhra Pradesh	2004590	13677	1977163	13750	0.68	98.63	0.69
35	West Bengal	1544109	9217	1516509	18383	0.60	98.21	1.19
3	Assam	585689	8005	572084	5600	1.37	97.68	0.96
25	Odisha	1002323	7461	987369	7493	0.74	98.51	0.75
23	Mizoram	54057	6664	47192	201	12.33	87.30	0.37
31	Telengana	655732	6276	645594	3862	0.96	98.45	0.59
21	Manipur	111598	3610	106229	1759	3.23	95.19	1.58
22	Meghalaya	74232	2820	70127	1285	3.80	94.47	1.73
12	Himachal Pradesh	212260	2054	206628	3578	0.97	97.35	1.69
29	Sikkim	29477	1548	27562	367	5.25	93.50	1.25
2	Arunachal Pradesh	52409	1127	51023	259	2.15	97.36	0.49
32	Tripura	82384	1113	80480	791	1.35	97.69	0.96
13	Jammu and Kashmir	324420	1055	318961	4404	0.33	98.32	1.36
9	Goa	173357	932	169239	3186	0.54	97.62	1.84
24	Nagaland	29669	888	28170	611	2.99	94.95	2.06
26	Puducherry	123007	765	120433	1809	0.62	97.91	1.47
11	Haryana	770380	664	760047	9669	0.09	98.66	1.26
6	Chhattisgarh	1004230	653	990022	13555	0.07	98.59	1.35
27	Punjab	600342	423	583564	16355	0.07	97.21	2.72
8	Delhi	1437485	411	1411995	25079	0.03	98.23	1.74
33	Uttar Pradesh	1709152	352	1686006	22794	0.02	98.65	1.33
34	Uttarakhand	342786	310	335099	7377	0.09	97.76	2.15
10	Gujarat	825330	160	815091	10079	0.02	98.76	1.22
14	Jharkhand	347755	153	342470	5132	0.04	98.48	1.48
28	Rajasthan	954040	128	944958	8954	0.01	99.05	0.94
4	Bihar	725605	102	715853	9650	0.01	98.66	1.33
19	Madhya Pradesh	792109	84	781509	10516	0.01	98.66	1.33
17	Ladakh	20500	55	20238	207	0.27	98.72	1.01
5	Chandigarh	65069	35	64222	812	0.05	98.70	1.25
18	Lakshadweep	10318	28	10239	51	0.27	99.23	0.49
0	Andaman and Nicobar	7560	10	7421	129	0.13	98.16	1.71
7	Dadra and Nagar Haveli and Daman and Diu	10659	4	10651	4	0.04	99.92	0.04

dataset.sort_values(["Death_Ratio"], ascending=False)
# dataset.head(5)

	State_UTs	Total_Cases	Active	Discharged	Deaths	Active_Ratio	Discharge_Ratio	Death_Ratio
27	Punjab	600342	423	583564	16355	0.07	97.21	2.72
34	Uttarakhand	342786	310	335099	7377	0.09	97.76	2.15
20	Maharashtra	6432649	53260	6243034	136355	0.83	97.05	2.12
24	Nagaland	29669	888	28170	611	2.99	94.95	2.06
9	Goa	173357	932	169239	3186	0.54	97.62	1.84
8	Delhi	1437485	411	1411995	25079	0.03	98.23	1.74
22	Meghalaya	74232	2820	70127	1285	3.80	94.47	1.73
0	Andaman and Nicobar	7560	10	7421	129	0.13	98.16	1.71
12	Himachal Pradesh	212260	2054	206628	3578	0.97	97.35	1.69
21	Manipur	111598	3610	106229	1759	3.23	95.19	1.58
14	Jharkhand	347755	153	342470	5132	0.04	98.48	1.48
26	Puducherry	123007	765	120433	1809	0.62	97.91	1.47
13	Jammu and Kashmir	324420	1055	318961	4404	0.33	98.32	1.36
6	Chhattisgarh	1004230	653	990022	13555	0.07	98.59	1.35
30	Tamil Nadu	2604074	18603	2550710	34761	0.71	97.95	1.33
4	Bihar	725605	102	715853	9650	0.01	98.66	1.33
19	Madhya Pradesh	792109	84	781509	10516	0.01	98.66	1.33
33	Uttar Pradesh	1709152	352	1686006	22794	0.02	98.65	1.33
15	Karnataka	2941026	19810	2884032	37184	0.67	98.06	1.26
11	Haryana	770380	664	760047	9669	0.09	98.66	1.26
5	Chandigarh	65069	35	64222	812	0.05	98.70	1.25
29	Sikkim	29477	1548	27562	367	5.25	93.50	1.25
10	Gujarat	825330	160	815091	10079	0.02	98.76	1.22
35	West Bengal	1544109	9217	1516509	18383	0.60	98.21	1.19
17	Ladakh	20500	55	20238	207	0.27	98.72	1.01
32	Tripura	82384	1113	80480	791	1.35	97.69	0.96
3	Assam	585689	8005	572084	5600	1.37	97.68	0.96
28	Rajasthan	954040	128	944958	8954	0.01	99.05	0.94
25	Odisha	1002323	7461	987369	7493	0.74	98.51	0.75
1	Andhra Pradesh	2004590	13677	1977163	13750	0.68	98.63	0.69
31	Telengana	655732	6276	645594	3862	0.96	98.45	0.59
16	Kerala	3851984	159870	3672357	19757	4.15	95.34	0.51
2	Arunachal Pradesh	52409	1127	51023	259	2.15	97.36	0.49
18	Lakshadweep	10318	28	10239	51	0.27	99.23	0.49
23	Mizoram	54057	6664	47192	201	12.33	87.30	0.37
7	Dadra and Nagar Haveli and Daman and Diu	10659	4	10651	4	0.04	99.92	0.04

dataset[["Total_Cases", "Deaths"]].sum(axis=0)

Total_Cases    32512366
Deaths           435758
dtype: int64

dataset.describe()

	Total_Cases	Active	Discharged	Deaths	Active_Ratio	Discharge_Ratio	Death_Ratio
count	3.600000e+01	36.000000	3.600000e+01	36.000000	36.000000	36.000000	36.000000
mean	9.031213e+05	8953.527778	8.820634e+05	12104.388889	1.263611	97.471667	1.265278
std	1.316180e+06	27649.920018	1.276942e+06	23385.359462	2.313456	2.239131	0.563770
min	7.560000e+03	4.000000	7.421000e+03	4.000000	0.010000	87.300000	0.040000
25%	7.194125e+04	158.250000	6.865075e+04	806.750000	0.065000	97.357500	0.955000
50%	4.667220e+05	910.000000	4.572770e+05	5366.000000	0.570000	98.185000	1.295000
75%	1.002800e+06	6373.000000	9.880322e+05	13603.750000	1.065000	98.652500	1.607500
max	6.432649e+06	159870.000000	6.243034e+06	136355.000000	12.330000	99.920000	2.720000

dataset.corr()

	Total_Cases	Active	Discharged	Deaths	Active_Ratio	Discharge_Ratio	Death_Ratio
Total_Cases	1.000000	0.657405	0.999924	0.904746	-0.083121	0.062078	0.092816
Active	0.657405	1.000000	0.649104	0.373963	0.217516	-0.181338	-0.173172
Discharged	0.999924	0.649104	1.000000	0.906137	-0.088095	0.066903	0.094055
Deaths	0.904746	0.373963	0.906137	1.000000	-0.125013	0.055103	0.292854
Active_Ratio	-0.083121	0.217516	-0.088095	-0.125013	1.000000	-0.969908	-0.251648
Discharge_Ratio	0.062078	-0.181338	0.066903	0.055103	-0.969908	1.000000	0.008449
Death_Ratio	0.092816	-0.173172	0.094055	0.292854	-0.251648	0.008449	1.000000

import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots

fig = make_subplots(rows=2, cols=2, subplot_titles= ["Total_Cases", "Deaths", "Active", "Discharged"])

total_cases = go.Histogram(x=dataset["Total_Cases"], nbinsx = 20, name = "Total_Cases")
Deaths = go.Histogram(x=dataset["Deaths"], nbinsx = 20, name = "Deaths")
Active = go.Histogram(x=dataset["Active"], nbinsx = 20, name = "Active")
Discharged = go.Histogram(x=dataset["Discharged"], nbinsx = 20, name = "Discharged")

fig.add_trace(total_cases, 1,1)
fig.add_trace(Deaths, 1,2)
fig.add_trace(Active, 2,1)
fig.add_trace(Discharged, 2,2)

fig.update_layout(showlegend = False)
fig.show()

fig = make_subplots(rows=2, cols=2, subplot_titles= ["Total_Cases", "Deaths", "Active", "Discharged"])

total_cases = go.Box(x=dataset["Total_Cases"],  name = "Total_Cases", text=dataset["State_UTs"])
Deaths = go.Box(x=dataset["Deaths"], name = "Deaths", text=dataset["Deaths"])
Active = go.Box(x=dataset["Active"], name = "Active", text=dataset["Active"])
Discharged = go.Box(x=dataset["Discharged"], name = "Discharged", text=dataset["Discharged"])

fig.add_trace(total_cases, 1,1)
fig.add_trace(Deaths, 1,2)
fig.add_trace(Active, 2,1)
fig.add_trace(Discharged, 2,2)

fig.update_layout(showlegend = False)
fig.show()

fig = make_subplots(rows=2, cols=2, subplot_titles= ["Total_Cases", "Deaths", "Active", "Discharged"])

total_cases = go.Bar(y=dataset["Total_Cases"],  name = "Total_Cases", hovertext=dataset["State_UTs"])
Deaths = go.Bar(y=dataset["Deaths"], name = "Deaths", hovertext=["Deaths"])
Active = go.Bar(y=dataset["Active"], name = "Active", hovertext=["Active"])
Discharged = go.Bar(y=dataset["Discharged"], name = "Discharged", hovertext=["Discharged"])

fig.add_trace(total_cases, 1,1)
fig.add_trace(Deaths, 1,2)
fig.add_trace(Active, 2,1)
fig.add_trace(Discharged, 2,2)

fig.update_layout(showlegend = False)
fig.show()

fig = go.Figure([go.Bar(y=dataset["Total_Cases"],  name = "Total_Cases", hovertext=dataset["State_UTs"],x=dataset["State_UTs"]), 
                 go.Bar(y=dataset["Discharged"], name = "Discharged", hovertext=["Discharged"], x=dataset["State_UTs"])])
fig.update_layout(barmode="group")
fig.update_layout(title="Total vs Discharged Cases")
fig.show()

fig = make_subplots(rows=2, cols=2, subplot_titles=["Total_Cases", "Deaths", "Active", "Discharged"], 
                    specs=[[{"type":"domain"},{"type":"domain"}],
                           [{"type":"domain"},{"type":"domain"}]])

total_cases = go.Pie(values=dataset["Total_Cases"],  name = "Total_Cases", labels=dataset["State_UTs"])
Deaths = go.Pie(values=dataset["Deaths"], name = "Deaths", labels=dataset["Deaths"])
Active = go.Pie(values=dataset["Active"], name = "Active", labels=dataset["Active"])
Discharged = go.Pie(values=dataset["Discharged"], name = "Discharged", labels=dataset["Discharged"])

fig.add_trace(total_cases, 1,1)
fig.add_trace(Deaths, 1,2)
fig.add_trace(Active, 2,1)
fig.add_trace(Discharged, 2,2)

fig.update_traces(hoverinfo="percent+label")

fig.update_layout(showlegend = False)
fig.update_traces(textposition = "inside")
fig = go.Figure(fig)
fig.show()

fig = go.Figure([go.Scatter(x=dataset["Total_Cases"], y=dataset["Deaths"], mode="markers", text=dataset["State_UTs"])])
fig.update_layout(title="Deats vs Total_Cases", xaxis_title="Total_Cases", yaxis_title="Deaths")
fig.show()

X = dataset["Total_Cases"].to_numpy()
Y = dataset["Deaths"].to_numpy()

X.shape, Y.shape

((36,), (36,))

# X = X.reshape((len(X),1))
# Y = Y.reshape((len(X),1))
# X.shape, Y.shape

from sklearn.linear_model import LinearRegression

model = LinearRegression()
# model.fit(X,Y)
model.fit(X.reshape((len(X),1)),Y)

(model.intercept_, model.coef_[0])

(-2413.4397885011676, 0.016075170671554388)

model.score(X.reshape((len(X),1)),Y)

0.8185661855516211

0.904746**2

0.8185653245160001

predictions = model.predict(X.reshape((len(X),1)))
predictions.shape

(36,)

fig = go.Figure([go.Scatter(x=dataset["Total_Cases"], y=dataset["Deaths"], mode="markers", text=dataset["State_UTs"], name= "Actual Deaths"),
                 go.Scatter(x=dataset["Total_Cases"], y=predictions, name = "Predicted Deaths")])
fig.update_layout(title="Deaths vs Total_Cases", xaxis_title="Total_Cases", yaxis_title="Deaths")
fig.show()